Convolutional Neural Networks

Project: Write an Algorithm for a Dog Identification App


In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. Sections that begin with '(IMPLEMENTATION)' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully!

Note: Once you have completed all of the code implementations, you need to finalize your work by exporting the Jupyter Notebook as an HTML document. Before exporting the notebook to html, all of the code cells need to have been run so that reviewers can see the final implementation and output. You can then export the notebook by using the menu above and navigating to File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.

In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question X' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.

Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. Markdown cells can be edited by double-clicking the cell to enter edit mode.

The rubric contains optional "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. If you decide to pursue the "Stand Out Suggestions", you should include the code in this Jupyter notebook.


Why We're Here

In this notebook, you will make the first steps towards developing an algorithm that could be used as part of a mobile or web app. At the end of this project, your code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling. The image below displays potential sample output of your finished project (... but we expect that each student's algorithm will behave differently!).

Sample Dog Output

In this real-world setting, you will need to piece together a series of models to perform different tasks; for instance, the algorithm that detects humans in an image will be different from the CNN that infers dog breed. There are many points of possible failure, and no perfect algorithm exists. Your imperfect solution will nonetheless create a fun user experience!

The Road Ahead

We break the notebook into separate steps. Feel free to use the links below to navigate the notebook.

  • Step 0: Import Datasets
  • Step 1: Detect Humans
  • Step 2: Detect Dogs
  • Step 3: Create a CNN to Classify Dog Breeds (from Scratch)
  • Step 4: Create a CNN to Classify Dog Breeds (using Transfer Learning)
  • Step 5: Write your Algorithm
  • Step 6: Test Your Algorithm

Step 0: Import Datasets

Make sure that you've downloaded the required human and dog datasets:

  • Download the dog dataset. Unzip the folder and place it in this project's home directory, at the location /dogImages.

  • Download the human dataset. Unzip the folder and place it in the home diretcory, at location /lfw.

Note: If you are using a Windows machine, you are encouraged to use 7zip to extract the folder.

In the code cell below, we save the file paths for both the human (LFW) dataset and dog dataset in the numpy arrays human_files and dog_files.

In [1]:
import numpy as np
from glob import glob

# load filenames for human and dog images
human_files = np.array(glob("data/lfw/*/*"))
dog_files = np.array(glob("data/dogImages/*/*/*"))

# print number of images in each dataset
print('There are %d total human images.' % len(human_files))
print('There are %d total dog images.' % len(dog_files))
There are 13233 total human images.
There are 8351 total dog images.

Step 1: Detect Humans

In this section, we use OpenCV's implementation of Haar feature-based cascade classifiers to detect human faces in images.

OpenCV provides many pre-trained face detectors, stored as XML files on github. We have downloaded one of these detectors and stored it in the haarcascades directory. In the next code cell, we demonstrate how to use this detector to find human faces in a sample image.

In [2]:
import cv2                
import matplotlib.pyplot as plt                        
%matplotlib inline                               

# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')

# load color (BGR) image
img = cv2.imread(human_files[0])
# convert BGR image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# find faces in image
faces = face_cascade.detectMultiScale(gray)

# print number of faces detected in the image
print('Number of faces detected:', len(faces))

# get bounding box for each detected face
for (x,y,w,h) in faces:
    # add bounding box to color image
    cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
    
# convert BGR image to RGB for plotting
cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

# display the image, along with bounding box
plt.imshow(cv_rgb)
plt.show()
Number of faces detected: 1

Before using any of the face detectors, it is standard procedure to convert the images to grayscale. The detectMultiScale function executes the classifier stored in face_cascade and takes the grayscale image as a parameter.

In the above code, faces is a numpy array of detected faces, where each row corresponds to a detected face. Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. The first two entries in the array (extracted in the above code as x and y) specify the horizontal and vertical positions of the top left corner of the bounding box. The last two entries in the array (extracted here as w and h) specify the width and height of the box.

Write a Human Face Detector

We can use this procedure to write a function that returns True if a human face is detected in an image and False otherwise. This function, aptly named face_detector, takes a string-valued file path to an image as input and appears in the code block below.

In [3]:
# returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
    img = cv2.imread(img_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray)
    return len(faces) > 0

(IMPLEMENTATION) Assess the Human Face Detector

Question 1: Use the code cell below to test the performance of the face_detector function.

  • What percentage of the first 100 images in human_files have a detected human face?
  • What percentage of the first 100 images in dog_files have a detected human face?

Ideally, we would like 100% of human images with a detected face and 0% of dog images with a detected face. You will see that our algorithm falls short of this goal, but still gives acceptable performance. We extract the file paths for the first 100 images from each of the datasets and store them in the numpy arrays human_files_short and dog_files_short.

Answer: (You can print out your results and/or write your percentages in this cell)

In [4]:
from tqdm import tqdm

human_files_short = human_files[:100]
dog_files_short = dog_files[:100]

#-#-# Do NOT modify the code above this line. #-#-#

## TODO: Test the performance of the face_detector algorithm 
## on the images in human_files_short and dog_files_short.
num = 100
human_faces_in_humans = 0
human_faces_in_dogs = 0
for i in tqdm(range(num)):
    human_faces_in_humans += face_detector(human_files_short[i])
    human_faces_in_dogs += face_detector(dog_files_short[i])

print("Human faces in humans photos: %d%%" % (100 * human_faces_in_humans // num))
print("Human faces in dogs photos: %d%%" % (100 * human_faces_in_dogs // num))
100%|████████████████████████████████████████████████████████████████████████████████| 100/100 [00:15<00:00,  6.53it/s]
Human faces in humans photos: 96%
Human faces in dogs photos: 17%

We suggest the face detector from OpenCV as a potential way to detect human images in your algorithm, but you are free to explore other approaches, especially approaches that make use of deep learning :). Please use the code cell below to design and test your own face detection algorithm. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.

In [5]:
### (Optional) 
### TODO: Test performance of anotherface detection algorithm.
### Feel free to use as many code cells as needed.

Step 2: Detect Dogs

In this section, we use a pre-trained model to detect dogs in images.

Obtain Pre-trained VGG-16 Model

The code cell below downloads the VGG-16 model, along with weights that have been trained on ImageNet, a very large, very popular dataset used for image classification and other vision tasks. ImageNet contains over 10 million URLs, each linking to an image containing an object from one of 1000 categories.

In [6]:
import torch
import torchvision.models as models

# define VGG16 model
VGG16 = models.vgg16(pretrained=True)

# check if CUDA is available
use_cuda = torch.cuda.is_available()

print("Cuda is available: ", use_cuda)

# move model to GPU if CUDA is available
if use_cuda:
    VGG16 = VGG16.cuda()
    
VGG16.eval()
pass
Cuda is available:  True

Given an image, this pre-trained VGG-16 model returns a prediction (derived from the 1000 possible categories in ImageNet) for the object that is contained in the image.

(IMPLEMENTATION) Making Predictions with a Pre-trained Model

In the next code cell, you will write a function that accepts a path to an image (such as 'dogImages/train/001.Affenpinscher/Affenpinscher_00001.jpg') as input and returns the index corresponding to the ImageNet class that is predicted by the pre-trained VGG-16 model. The output should always be an integer between 0 and 999, inclusive.

Before writing the function, make sure that you take the time to learn how to appropriately pre-process tensors for pre-trained models in the PyTorch documentation.

In [7]:
from PIL import Image
import torchvision.transforms as transforms

def VGG16_predict(img_path):
    '''
    Use pre-trained VGG-16 model to obtain index corresponding to 
    predicted ImageNet class for image at specified path
    
    Args:
        img_path: path to an image
        
    Returns:
        Index corresponding to VGG-16 model's prediction
    '''
    
    ## TODO: Complete the function.
    ## Load and pre-process an image from the given img_path
    ## Return the *index* of the predicted class for that image

    # See generic_predict function
    return generic_dog_predict(VGG16, img_path) # predicted class index

# This function allows passing different models to classify image
def generic_dog_predict(model, img_path, sz=224, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]):
    img = Image.open(img_path)
    # Image transformations
    transform = transforms.Compose([
        transforms.Resize(sz),
        transforms.CenterCrop(sz),
        transforms.ToTensor(),
        transforms.Normalize(mean=mean, std=std)
    ])
    img_norm = transform(img).unsqueeze_(0)
    if use_cuda:
        img_norm = img_norm.cuda()
    with torch.no_grad():
         outputs = model(img_norm).cpu().numpy()
    top_class = np.argmax(outputs)
    return top_class

(IMPLEMENTATION) Write a Dog Detector

While looking at the dictionary, you will notice that the categories corresponding to dogs appear in an uninterrupted sequence and correspond to dictionary keys 151-268, inclusive, to include all categories from 'Chihuahua' to 'Mexican hairless'. Thus, in order to check to see if an image is predicted to contain a dog by the pre-trained VGG-16 model, we need only check if the pre-trained model predicts an index between 151 and 268 (inclusive).

Use these ideas to complete the dog_detector function below, which returns True if a dog is detected in an image (and False if not).

In [8]:
### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
    ## TODO: Complete the function.
    # Pass VGG16 model into detector
    return generic_dog_detector(VGG16_predict, img_path)

# This function takes in predicting function and runs it on the image
# It assumes the predicting function returns ImageNet class
# And returns True if the predicted class is in dogs range
def generic_dog_detector(predict, img_path):
    pred = predict(img_path)
    imn_dogs_start_idx = 151
    imn_dogs_end_idx = 268
    is_dog = imn_dogs_start_idx <= pred <= imn_dogs_end_idx
    return is_dog
    

(IMPLEMENTATION) Assess the Dog Detector

Question 2: Use the code cell below to test the performance of your dog_detector function.

  • What percentage of the images in human_files_short have a detected dog?
  • What percentage of the images in dog_files_short have a detected dog?

Answer:

In [9]:
### TODO: Test the performance of the dog_detector function
### on the images in human_files_short and dog_files_short.

num = 100
dogs_in_humans = 0
dogs_in_dogs = 0
for i in tqdm(range(num)):
    dogs_in_humans += dog_detector(human_files_short[i])
    dogs_in_dogs += dog_detector(dog_files_short[i])

print("Dogs detected in humans photos: %d%%" % (100 * dogs_in_humans // num))
print("Dogs detected in dogs photos: %d%%" % (100 * dogs_in_dogs // num))
100%|████████████████████████████████████████████████████████████████████████████████| 100/100 [00:05<00:00, 24.35it/s]
Dogs detected in humans photos: 0%
Dogs detected in dogs photos: 93%

We suggest VGG-16 as a potential network to detect dog images in your algorithm, but you are free to explore other pre-trained networks (such as Inception-v3, ResNet-50, etc). Please use the code cell below to test other pre-trained PyTorch models. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.

In [10]:
### (Optional) 
### TODO: Report the performance of another pre-trained network.
### Feel free to use as many code cells as needed.

# Let's check resnet50 model
resnet50 = models.resnet50(pretrained=True)
# move model to GPU if CUDA is available
if use_cuda:
    resnet50 = resnet50.cuda()
    
resnet50.eval()

def resnet50_predict(img_path):
    return generic_dog_predict(resnet50, img_path)

def dog_detector_resnet(img_path):
    return generic_dog_detector(resnet50_predict, img_path)

num = 100
dogs_in_humans = 0
dogs_in_dogs = 0
for i in tqdm(range(num)):
    dogs_in_humans += dog_detector_resnet(human_files_short[i])
    dogs_in_dogs += dog_detector_resnet(dog_files_short[i])

print("Dogs detected in humans photos (resnet50): %d%%" % (100 * dogs_in_humans // num))
print("Dogs detected in dogs photos (resnet50): %d%%" % (100 * dogs_in_dogs // num))
100%|████████████████████████████████████████████████████████████████████████████████| 100/100 [00:09<00:00, 10.26it/s]
Dogs detected in humans photos (resnet50): 1%
Dogs detected in dogs photos (resnet50): 96%

Step 3: Create a CNN to Classify Dog Breeds (from Scratch)

Now that we have functions for detecting humans and dogs in images, we need a way to predict breed from images. In this step, you will create a CNN that classifies dog breeds. You must create your CNN from scratch (so, you can't use transfer learning yet!), and you must attain a test accuracy of at least 10%. In Step 4 of this notebook, you will have the opportunity to use transfer learning to create a CNN that attains greatly improved accuracy.

We mention that the task of assigning breed to dogs from images is considered exceptionally challenging. To see why, consider that even a human would have trouble distinguishing between a Brittany and a Welsh Springer Spaniel.

Brittany Welsh Springer Spaniel

It is not difficult to find other dog breed pairs with minimal inter-class variation (for instance, Curly-Coated Retrievers and American Water Spaniels).

Curly-Coated Retriever American Water Spaniel

Likewise, recall that labradors come in yellow, chocolate, and black. Your vision-based algorithm will have to conquer this high intra-class variation to determine how to classify all of these different shades as the same breed.

Yellow Labrador Chocolate Labrador Black Labrador

We also mention that random chance presents an exceptionally low bar: setting aside the fact that the classes are slightly imabalanced, a random guess will provide a correct answer roughly 1 in 133 times, which corresponds to an accuracy of less than 1%.

Remember that the practice is far ahead of the theory in deep learning. Experiment with many different architectures, and trust your intuition. And, of course, have fun!

(IMPLEMENTATION) Specify Data Loaders for the Dog Dataset

Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dogImages/train, dogImages/valid, and dogImages/test, respectively). You may find this documentation on custom datasets to be a useful resource. If you are interested in augmenting your training and/or validation data, check out the wide variety of transforms!

In [11]:
import os
from torchvision import datasets
from PIL import ImageFile
import pickle

### TODO: Write data loaders for training, validation, and test sets
## Specify appropriate transforms, and batch_sizes

# I needed to add this custom dataset that just sets ImageFile.LOAD_TRUNCATED_IMAGES = True
# It is required to run num_workers>1 for image loader, otherwise LOAD_TRUNCATED_IMAGES doesn't apply in workers
# LOAD_TRUNCATED_IMAGES is needed to avoid error when images are loaded
from  RobustImageFolder import RobustImageFolder

# This function calculates mean and std for train provided path
# These values will be used for images normalization
def calc_mean_std(path, bs=64, size=224):
    transform = transforms.Compose([
        transforms.Resize(size),
        transforms.CenterCrop(size),
        transforms.ToTensor()
    ])
    dataset = RobustImageFolder(path, transform=transform)
    loader = torch.utils.data.DataLoader(dataset, batch_size=bs, num_workers=4)
    mean = torch.zeros(3)
    std = torch.zeros(3)
    count = 0
    for data in loader:
        # get image data
        data = data[0]
        # flatten
        data = data.view(data.shape[0], data.shape[1], -1)
        # calc mean & std per channel and sum over batch dimension
        mean += data.mean(2).sum(0)
        std += data.std(2).sum(0)
        count += data.shape[0]

    mean /= count
    std /= count
    return mean.numpy().tolist(), std.numpy().tolist()

# This function creates loader and can be re-used to make different kind of loaders that use same transforms
def make_loader(path, bs=64, size=224, rot_deg = 5, norm=None, train=False):
    tmfs = []
    if train:
        # Train loader should do augmentation
        tmfs = [
            transforms.RandomRotation(rot_deg),
            transforms.RandomResizedCrop(size),
            transforms.RandomHorizontalFlip()
        ]
    else:
        # Test/validation loaders won't do augmentation
        tmfs = [
            transforms.Resize(size),
            transforms.CenterCrop(size)
        ]
    tmfs.append(transforms.ToTensor())
    tmfs.append(transforms.Normalize(mean = norm['mean'], std = norm['std']))
    transform = transforms.Compose(tmfs)
    dataset = RobustImageFolder(path, transform=transform)
    loader = torch.utils.data.DataLoader(dataset, batch_size=bs, shuffle=True, num_workers=4)
    return loader

# paths
data_path = 'data/dogImages/'
train_path = data_path + 'train'
val_path = data_path + 'valid'
test_path = data_path + 'test'

# batch size
bs = 64

# image size
size = 224

# create simpliest train dataset to extract classes
train_dataset = datasets.ImageFolder(train_path)
dogs_classes = train_dataset.classes
dogs_classes_count = len(dogs_classes)

# we'll cache mean/std of train dataset to avoid calculating it each time
mean_std_cache = data_path + 'mean_std.dump'
if os.path.exists(mean_std_cache):
    # load from cache
    norm = pickle.load(open(mean_std_cache, 'rb'))
else:
    # calculate
    mean, std = calc_mean_std(train_path, bs=bs, size=size)
    norm = {'mean': mean, 'std': std}
    # store in cache file
    pickle.dump(norm, open(mean_std_cache, 'wb'))

# debug
print('normalization for train:', norm)

# Create loaders for scratch model
loaders_scratch = {
    'train': make_loader(train_path, bs=bs, size=size, norm=norm, train=True),
    'valid': make_loader(val_path, bs=bs, size=size, norm=norm),
    'test': make_loader(test_path, bs=bs, size=size, norm=norm)
}
normalization for train: {'mean': [0.48805874586105347, 0.46292823553085327, 0.39578890800476074], 'std': [0.2300969362258911, 0.22556865215301514, 0.22421854734420776]}

Question 3: Describe your chosen procedure for preprocessing the data.

  • How does your code resize the images (by cropping, stretching, etc)? What size did you pick for the input tensor, and why?
  • Did you decide to augment the dataset? If so, how (through translations, flips, rotations, etc)? If not, why not?

Answer:

For training data, I resize images using torchvision transformer RandomResizedCrop, which makes randomly scaled patches of image resized to the specified size. For validation/test datasets, I resize smallest side to 224 and do CenterCrop tranformation to make square image. I decided to go with "standard" input size that is used for many other well-known models - 224x224. This way I can also compare my model to other existing models, e.g. the one used for transfer learning task :)

Other transformations are common for both train and validation/test datasets - converting to torch tensor and normalizing using mean and std pre-calculated on the train dataset.

As additional augmentation, I use RandomRotation and RandomHorizontalFlip transforms. These transformations are natural for photos and should improve the model robustness.

(IMPLEMENTATION) Model Architecture

Create a CNN to classify dog breed. Use the template in the code cell below.

In [12]:
import torch.nn as nn
import torch.nn.functional as F

# define the CNN architecture
class Net(nn.Module):
    ### TODO: choose an architecture, and complete the class
    def __init__(self):
        super(Net, self).__init__()
        ## Define layers of a CNN
        self.conv1 = nn.Conv2d(3, 32, 7, 2)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.conv3 = nn.Conv2d(64, 128, 3, 1)
        self.fc1 = nn.Linear(128 * 12 * 12, 2000)
        self.fc2 = nn.Linear(2000, dogs_classes_count)
        self.bn1 = nn.BatchNorm2d(32)
        self.bn2 = nn.BatchNorm2d(64)
        self.bn3 = nn.BatchNorm2d(128)

    def forward(self, x):
        ## Define forward behavior
        x = self.bn1(self.conv1(x)) # 106
        x = F.relu(F.max_pool2d(x, 2)) # 53
        x = self.bn2(self.conv2(x)) # 51
        x = F.relu(F.max_pool2d(x, 2)) # 25
        x = self.bn3(self.conv3(x)) # 23
        x = F.relu(F.max_pool2d(x, 2)) # 12
        # flatten
        x = x.view(x.size(0), -1)
        x = F.dropout(x, p=0.2, training=self.training)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, p=0.2, training=self.training)
        x = self.fc2(x)
        x = F.log_softmax(x, dim=1)
        return x

#-#-# You so NOT have to modify the code below this line. #-#-#

# instantiate the CNN
model_scratch = Net()

# move tensors to GPU if CUDA is available
if use_cuda:
    model_scratch = model_scratch.cuda()

Question 4: Outline the steps you took to get to your final CNN architecture and your reasoning at each step.

Answer:

I decided to go with pretty standard convolutional net architecture, not very deep so it can be easily trained. It's somewhat close to one classic model for MNIST recognition, but have more params. There're 3 similar blocks having same operations:

  • Convolution (each block doubles number of channels: 32->64->128, this is common rule of thumb to increase channels with each layer)
  • Batch Normalization (improves training process by normalizing layer outputs)
  • Max Pooling (2x2, to reduce number of params)
  • ReLU (commonly used activation function)

These 3 blocks consecutively shrink input image into tensor with dimensions 128x12x12. When trained, such blocks should transform the input image into representation of image features. After that, we flatten the resulting tensor and use 2 fully connected layers of sizes 2000 and 133 with dropouts in between (Dropout is good regularization and ensembling technique). These last layers should do classification task on image features created by convolution layers.

The final output is passed through softmax (probability of classes) followed by log (to work well with pytorch loss function NLLLoss(), because NLLLoss() does not apply log, we apply it with log_softmax()).

(IMPLEMENTATION) Specify Loss Function and Optimizer

Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_scratch, and the optimizer as optimizer_scratch below.

In [13]:
import torch.optim as optim

lr = 0.001
momentum = 0.9
wd = 0.0001

### TODO: select loss function
criterion_scratch = torch.nn.NLLLoss()
if use_cuda:
    criterion_scratch.cuda()

### TODO: select optimizer
optimizer_scratch = optim.SGD(model_scratch.parameters(), lr=lr, momentum=momentum, weight_decay=wd)
    

(IMPLEMENTATION) Train and Validate the Model

Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_scratch.pt'.

In [14]:
def train(n_epochs, loaders, model, optimizer, criterion, use_cuda, save_path):
    """returns trained model"""
    # initialize tracker for minimum validation loss
    valid_loss_min = np.Inf 
    
    for epoch in range(1, n_epochs+1):
        # initialize variables to monitor training and validation loss
        train_loss = 0.0
        valid_loss = 0.0
        
        ###################
        # train the model #
        ###################
        model.train()
        for batch_idx, (data, target) in enumerate(loaders['train']):
            # move to GPU
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            ## find the loss and update the model parameters accordingly
            ## record the average training loss, using something like
            optimizer.zero_grad()
            output = model(data)
            loss = criterion(output, target)
            loss.backward()
            optimizer.step()
            train_loss = train_loss + ((1 / (batch_idx + 1)) * (loss.data - train_loss))
            
        ######################    
        # validate the model #
        ######################
        model.eval()
        for batch_idx, (data, target) in enumerate(loaders['valid']):
            # move to GPU
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            ## update the average validation loss
            output = model(data)
            loss = criterion(output, target)
            valid_loss = valid_loss + ((1 / (batch_idx + 1)) * (loss.data - valid_loss))
            
        # print training/validation statistics 
        print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
            epoch, 
            train_loss,
            valid_loss
            ))
        
        ## TODO: save the model if validation loss has decreased
        if valid_loss_min > valid_loss:
            torch.save(model.state_dict(), save_path)
            valid_loss_min = valid_loss
        
    # return trained model
    return model


# train the model
n_epochs = 80
model_scratch = train(n_epochs, loaders_scratch, model_scratch, optimizer_scratch, 
                      criterion_scratch, use_cuda, data_path + 'model_scratch.pt')

# load the model that got the best validation accuracy
model_scratch.load_state_dict(torch.load(data_path + 'model_scratch.pt'))
Epoch: 1 	Training Loss: 4.842552 	Validation Loss: 4.731898
Epoch: 2 	Training Loss: 4.672561 	Validation Loss: 4.588732
Epoch: 3 	Training Loss: 4.560332 	Validation Loss: 4.505441
Epoch: 4 	Training Loss: 4.486170 	Validation Loss: 4.401400
Epoch: 5 	Training Loss: 4.428969 	Validation Loss: 4.294973
Epoch: 6 	Training Loss: 4.365345 	Validation Loss: 4.300364
Epoch: 7 	Training Loss: 4.313652 	Validation Loss: 4.163656
Epoch: 8 	Training Loss: 4.275823 	Validation Loss: 4.132354
Epoch: 9 	Training Loss: 4.221452 	Validation Loss: 4.233955
Epoch: 10 	Training Loss: 4.185470 	Validation Loss: 4.096782
Epoch: 11 	Training Loss: 4.148946 	Validation Loss: 3.991061
Epoch: 12 	Training Loss: 4.100498 	Validation Loss: 3.994202
Epoch: 13 	Training Loss: 4.085329 	Validation Loss: 4.094252
Epoch: 14 	Training Loss: 4.056415 	Validation Loss: 4.014763
Epoch: 15 	Training Loss: 3.998815 	Validation Loss: 4.034421
Epoch: 16 	Training Loss: 3.982538 	Validation Loss: 3.980682
Epoch: 17 	Training Loss: 3.935329 	Validation Loss: 3.901443
Epoch: 18 	Training Loss: 3.899078 	Validation Loss: 3.845285
Epoch: 19 	Training Loss: 3.870891 	Validation Loss: 3.902212
Epoch: 20 	Training Loss: 3.843222 	Validation Loss: 3.902345
Epoch: 21 	Training Loss: 3.831522 	Validation Loss: 3.731912
Epoch: 22 	Training Loss: 3.825245 	Validation Loss: 3.744742
Epoch: 23 	Training Loss: 3.772745 	Validation Loss: 3.783360
Epoch: 24 	Training Loss: 3.770801 	Validation Loss: 3.786512
Epoch: 25 	Training Loss: 3.733301 	Validation Loss: 3.737102
Epoch: 26 	Training Loss: 3.701267 	Validation Loss: 3.701827
Epoch: 27 	Training Loss: 3.665480 	Validation Loss: 3.725989
Epoch: 28 	Training Loss: 3.648038 	Validation Loss: 3.666092
Epoch: 29 	Training Loss: 3.633303 	Validation Loss: 3.624831
Epoch: 30 	Training Loss: 3.600927 	Validation Loss: 3.582834
Epoch: 31 	Training Loss: 3.587362 	Validation Loss: 3.678218
Epoch: 32 	Training Loss: 3.556342 	Validation Loss: 3.706354
Epoch: 33 	Training Loss: 3.544734 	Validation Loss: 3.684534
Epoch: 34 	Training Loss: 3.496946 	Validation Loss: 3.699986
Epoch: 35 	Training Loss: 3.492864 	Validation Loss: 3.587668
Epoch: 36 	Training Loss: 3.474398 	Validation Loss: 3.472212
Epoch: 37 	Training Loss: 3.455498 	Validation Loss: 3.552349
Epoch: 38 	Training Loss: 3.420680 	Validation Loss: 3.517396
Epoch: 39 	Training Loss: 3.417296 	Validation Loss: 3.669919
Epoch: 40 	Training Loss: 3.411947 	Validation Loss: 3.493543
Epoch: 41 	Training Loss: 3.369741 	Validation Loss: 3.506039
Epoch: 42 	Training Loss: 3.330993 	Validation Loss: 3.652468
Epoch: 43 	Training Loss: 3.330636 	Validation Loss: 3.405568
Epoch: 44 	Training Loss: 3.311551 	Validation Loss: 3.665996
Epoch: 45 	Training Loss: 3.306827 	Validation Loss: 3.552514
Epoch: 46 	Training Loss: 3.273741 	Validation Loss: 3.549520
Epoch: 47 	Training Loss: 3.266918 	Validation Loss: 3.338560
Epoch: 48 	Training Loss: 3.217253 	Validation Loss: 3.645970
Epoch: 49 	Training Loss: 3.227607 	Validation Loss: 3.344458
Epoch: 50 	Training Loss: 3.237580 	Validation Loss: 3.461755
Epoch: 51 	Training Loss: 3.194485 	Validation Loss: 3.525734
Epoch: 52 	Training Loss: 3.182600 	Validation Loss: 3.467916
Epoch: 53 	Training Loss: 3.162056 	Validation Loss: 3.397780
Epoch: 54 	Training Loss: 3.121219 	Validation Loss: 3.298227
Epoch: 55 	Training Loss: 3.118243 	Validation Loss: 3.351590
Epoch: 56 	Training Loss: 3.113464 	Validation Loss: 3.442025
Epoch: 57 	Training Loss: 3.117767 	Validation Loss: 3.378122
Epoch: 58 	Training Loss: 3.083925 	Validation Loss: 3.340072
Epoch: 59 	Training Loss: 3.060272 	Validation Loss: 3.429613
Epoch: 60 	Training Loss: 3.047140 	Validation Loss: 3.373405
Epoch: 61 	Training Loss: 3.023648 	Validation Loss: 3.282917
Epoch: 62 	Training Loss: 3.027438 	Validation Loss: 3.243526
Epoch: 63 	Training Loss: 3.011046 	Validation Loss: 3.250624
Epoch: 64 	Training Loss: 3.016323 	Validation Loss: 3.253841
Epoch: 65 	Training Loss: 2.957799 	Validation Loss: 3.411931
Epoch: 66 	Training Loss: 2.934693 	Validation Loss: 3.245306
Epoch: 67 	Training Loss: 2.932981 	Validation Loss: 3.427890
Epoch: 68 	Training Loss: 2.935114 	Validation Loss: 3.113845
Epoch: 69 	Training Loss: 2.924222 	Validation Loss: 3.360450
Epoch: 70 	Training Loss: 2.908463 	Validation Loss: 3.181529
Epoch: 71 	Training Loss: 2.876349 	Validation Loss: 3.390890
Epoch: 72 	Training Loss: 2.879836 	Validation Loss: 3.502774
Epoch: 73 	Training Loss: 2.854120 	Validation Loss: 3.480636
Epoch: 74 	Training Loss: 2.833680 	Validation Loss: 3.105767
Epoch: 75 	Training Loss: 2.818323 	Validation Loss: 3.224580
Epoch: 76 	Training Loss: 2.807402 	Validation Loss: 3.317370
Epoch: 77 	Training Loss: 2.789694 	Validation Loss: 3.143685
Epoch: 78 	Training Loss: 2.787806 	Validation Loss: 3.295967
Epoch: 79 	Training Loss: 2.750886 	Validation Loss: 3.149904
Epoch: 80 	Training Loss: 2.731750 	Validation Loss: 3.150805

(IMPLEMENTATION) Test the Model

Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 10%.

In [15]:
def test(loaders, model, criterion, use_cuda):

    # monitor test loss and accuracy
    test_loss = 0.
    correct = 0.
    total = 0.

    model.eval()
    for batch_idx, (data, target) in enumerate(loaders['test']):
        # move to GPU
        if use_cuda:
            data, target = data.cuda(), target.cuda()
        # forward pass: compute predicted outputs by passing inputs to the model
        output = model(data)
        # calculate the loss
        loss = criterion(output, target)
        # update average test loss 
        test_loss = test_loss + ((1 / (batch_idx + 1)) * (loss.data - test_loss))
        # convert output probabilities to predicted class
        pred = output.data.max(1, keepdim=True)[1]
        # compare predictions to true label
        correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
        total += data.size(0)
            
    print('Test Loss: {:.6f}\n'.format(test_loss))

    print('\nTest Accuracy: %2d%% (%2d/%2d)' % (
        100. * correct / total, correct, total))

# call test function    
test(loaders_scratch, model_scratch, criterion_scratch, use_cuda)
Test Loss: 3.186315


Test Accuracy: 22% (188/836)

Step 4: Create a CNN to Classify Dog Breeds (using Transfer Learning)

You will now use transfer learning to create a CNN that can identify dog breed from images. Your CNN must attain at least 60% accuracy on the test set.

(IMPLEMENTATION) Specify Data Loaders for the Dog Dataset

Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dogImages/train, dogImages/valid, and dogImages/test, respectively).

If you like, you are welcome to use the same data loaders from the previous step, when you created a CNN from scratch.

In [16]:
## TODO: Specify data loaders
# since this is imagenet-trained model, use imagenet normalization values
image_net_norm = {'mean': [0.485, 0.456, 0.406], 'std': [0.229, 0.224, 0.225]}
loaders_transfer = {
    'train': make_loader(train_path, bs=bs, size=size, norm=image_net_norm, train=True),
    'valid': make_loader(val_path, bs=bs, size=size, norm=image_net_norm),
    'test': make_loader(test_path, bs=bs, size=size, norm=image_net_norm)
}

(IMPLEMENTATION) Model Architecture

Use transfer learning to create a CNN to classify dog breed. Use the code cell below, and save your initialized model as the variable model_transfer.

In [17]:
import torchvision.models as models
import torch.nn as nn

## TODO: Specify model architecture 
model_transfer = models.resnet50(pretrained=True)

# freeze all params
for param in model_transfer.parameters():
    param.requires_grad = False

# replace the last layer
model_transfer.fc = nn.Linear(2048, dogs_classes_count)
 
if use_cuda:
    model_transfer = model_transfer.cuda()

Question 5: Outline the steps you took to get to your final CNN architecture and your reasoning at each step. Describe why you think the architecture is suitable for the current problem.

Answer:

I took resnet50 as "backbone" model because it's relatively small and fast but has good accuracy. All the layers were frozen, except the last fully connected layer was replaced with untrained fully connected layer to classify dog breeds from 2048 image features produced by backbone model.

Since this resnet50 model is already trained on ImageNet and "knows" some dog breeds, re-tuning it to recognize dog breeds only (plus some additional dog breeds granularity) should work nicely.

It might also make sense to unfreeze some of the last layers to fine-tune them for dog breeds task as well, but I don't do that to make training process faster.

(IMPLEMENTATION) Specify Loss Function and Optimizer

Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_transfer, and the optimizer as optimizer_transfer below.

In [18]:
criterion_transfer = nn.CrossEntropyLoss()
if use_cuda:
    criterion_transfer = criterion_transfer.cuda()

optimizer_transfer = optim.Adam(model_transfer.fc.parameters(), weight_decay=0.001)

(IMPLEMENTATION) Train and Validate the Model

Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_transfer.pt'.

In [19]:
# train the model
n_epochs = 30
model_transfer = train(n_epochs, loaders_transfer, model_transfer, optimizer_transfer, criterion_transfer, use_cuda, data_path + 'model_transfer.pt')

# load the model that got the best validation accuracy (uncomment the line below)
model_transfer.load_state_dict(torch.load(data_path + 'model_transfer.pt'))
Epoch: 1 	Training Loss: 2.776066 	Validation Loss: 0.995175
Epoch: 2 	Training Loss: 1.242128 	Validation Loss: 0.644768
Epoch: 3 	Training Loss: 1.008785 	Validation Loss: 0.552935
Epoch: 4 	Training Loss: 0.911420 	Validation Loss: 0.497870
Epoch: 5 	Training Loss: 0.844615 	Validation Loss: 0.483233
Epoch: 6 	Training Loss: 0.794779 	Validation Loss: 0.453462
Epoch: 7 	Training Loss: 0.754274 	Validation Loss: 0.460231
Epoch: 8 	Training Loss: 0.732631 	Validation Loss: 0.457302
Epoch: 9 	Training Loss: 0.737173 	Validation Loss: 0.495864
Epoch: 10 	Training Loss: 0.709334 	Validation Loss: 0.403517
Epoch: 11 	Training Loss: 0.678571 	Validation Loss: 0.389704
Epoch: 12 	Training Loss: 0.680011 	Validation Loss: 0.374519
Epoch: 13 	Training Loss: 0.653505 	Validation Loss: 0.483177
Epoch: 14 	Training Loss: 0.678715 	Validation Loss: 0.422971
Epoch: 15 	Training Loss: 0.655148 	Validation Loss: 0.405705
Epoch: 16 	Training Loss: 0.627675 	Validation Loss: 0.434054
Epoch: 17 	Training Loss: 0.650503 	Validation Loss: 0.501961
Epoch: 18 	Training Loss: 0.621588 	Validation Loss: 0.442704
Epoch: 19 	Training Loss: 0.626350 	Validation Loss: 0.399981
Epoch: 20 	Training Loss: 0.623809 	Validation Loss: 0.412491
Epoch: 21 	Training Loss: 0.624993 	Validation Loss: 0.414510
Epoch: 22 	Training Loss: 0.623051 	Validation Loss: 0.489910
Epoch: 23 	Training Loss: 0.614288 	Validation Loss: 0.500156
Epoch: 24 	Training Loss: 0.625543 	Validation Loss: 0.435221
Epoch: 25 	Training Loss: 0.621156 	Validation Loss: 0.400487
Epoch: 26 	Training Loss: 0.603945 	Validation Loss: 0.415545
Epoch: 27 	Training Loss: 0.602903 	Validation Loss: 0.434705
Epoch: 28 	Training Loss: 0.601816 	Validation Loss: 0.398124
Epoch: 29 	Training Loss: 0.561235 	Validation Loss: 0.447086
Epoch: 30 	Training Loss: 0.595203 	Validation Loss: 0.387845

(IMPLEMENTATION) Test the Model

Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 60%.

In [20]:
test(loaders_transfer, model_transfer, criterion_transfer, use_cuda)
Test Loss: 0.451425


Test Accuracy: 85% (711/836)

(IMPLEMENTATION) Predict Dog Breed with the Model

Write a function that takes an image path as input and returns the dog breed (Affenpinscher, Afghan hound, etc) that is predicted by your model.

In [21]:
### TODO: Write a function that takes a path to an image as input
### and returns the dog breed that is predicted by the model.

# list of class names by index, i.e. a name can be accessed like class_names[0]
class_names = [item[4:].replace("_", " ") for item in dogs_classes]

# Img can be path or PIL Image
def predict_breed_transfer(img):
    # load the image and return the predicted breed
    if not Image.isImageType(img):
        img = Image.open(img)
    tfms = transforms.Compose([
        transforms.Resize(size),
        transforms.CenterCrop(size),
        transforms.ToTensor(),
        transforms.Normalize(mean=image_net_norm['mean'], std=image_net_norm['std'])
    ])
    inp = tfms(img).unsqueeze_(0)
    if use_cuda:
        inp = inp.cuda()
    with torch.no_grad():
        output = model_transfer(inp)
    res = np.argmax(output.cpu().numpy())
    return class_names[res]

Step 5: Write your Algorithm

Write an algorithm that accepts a file path to an image and first determines whether the image contains a human, dog, or neither. Then,

  • if a dog is detected in the image, return the predicted breed.
  • if a human is detected in the image, return the resembling dog breed.
  • if neither is detected in the image, provide output that indicates an error.

You are welcome to write your own functions for detecting humans and dogs in images, but feel free to use the face_detector and human_detector functions developed above. You are required to use your CNN from Step 4 to predict dog breed.

Some sample output for our algorithm is provided below, but feel free to design your own user experience!

Sample Human Output

(IMPLEMENTATION) Write your Algorithm

In [22]:
### TODO: Write your algorithm.
### Feel free to use as many code cells as needed.

from IPython.core.display import display, HTML

def run_app(img_path):
    ## handle cases for a human face, dog, and neither
    is_dog = dog_detector_resnet(img_path)
    is_person = face_detector(img_path) if not is_dog else False

    # Predict breed
    dog_class = predict_breed_transfer(img_path)
    # Create link to google images to easily check for other images of breed
    dog_class_link = HTML("<a href='https://www.google.com/search?tbm=isch&q=%(dog)s'>%(dog)s</a>" % {'dog': dog_class })
    if is_person:
        print("Hi Human!")
        plt.imshow(Image.open(img_path))
        plt.show()
        print("You look like a ... ")
        display(dog_class_link)
    elif is_dog:
        plt.imshow(Image.open(img_path))
        plt.show()
        print("This dog's breed is ...")
        display(dog_class_link)
    else:
        # neither
        print("Could not find anything interesting on your image :(")
        plt.imshow(Image.open(img_path))
        plt.show()
        print("But if you ask, it looks like ...")
        display(dog_class_link)
      

Step 6: Test Your Algorithm

In this section, you will take your new algorithm for a spin! What kind of dog does the algorithm think that you look like? If you have a dog, does it predict your dog's breed accurately? If you have a cat, does it mistakenly think that your cat is a dog?

(IMPLEMENTATION) Test Your Algorithm on Sample Images!

Test your algorithm at least six images on your computer. Feel free to use any images you like. Use at least two human and two dog images.

Question 6: Is the output better than you expected :) ? Or worse :( ? Provide at least three possible points of improvement for your algorithm.

Answer:

  1. Performance for dog breeds seems good even with hard cases where part of the dog is occluded. Also the resnet50 model for dogs detection didn't buy into fake dogs images but fine-tuned model provided rather close-looking predictions for them :)

  2. Guessing dogs breeds for human images is a bit disappointing :) It seems that the model does not really catch "high-level" similarity but rather texture/color.

  3. Possible improvements:

    • The main drawback is that the model expects only one dog per image. If there're multiple dogs of different breeds the prediction can be wrong for all of them. To improve on that, my stretch goal for this project is to use segmentation to first extract each dog (or person) from the image and then apply dog breed recognition model!
    • The app itself can only choose between person or dog, and can't do both, for example. When image has both face and dog it would be nice to provide prediction for both. This item can be also covered by segmentation step in the pipeline.
    • Not all dog breeds are present in the training dataset. It could be expanded by downloading images from the internet to make predictions more accurate.
    • To provide more initeresting results for "human as dog" recognition, maybe it makes sense to create separate model for "human as dog" prediction that will be trained or tuned on additional datasets like these: https://petapixel.com/2018/09/20/photos-of-humans-and-dogs-who-look-strangely-alike/, https://www.wideopenpets.com/15-people-look-like-dogs/
In [23]:
## TODO: Execute your algorithm from Step 6 on
## at least 6 images on your computer.
## Feel free to use as many code cells as needed.

from glob import glob

for file in glob('test/**/*.jpg'):
    run_app(file)
    print('=============================')
This dog's breed is ...
=============================
This dog's breed is ...
=============================
This dog's breed is ...
=============================
This dog's breed is ...
=============================
Could not find anything interesting on your image :(
But if you ask, it looks like ...
=============================
This dog's breed is ...
=============================
This dog's breed is ...
=============================
This dog's breed is ...
=============================
Hi Human!
You look like a ... 
=============================
Hi Human!
You look like a ... 
=============================
Hi Human!
You look like a ... 
=============================
Hi Human!
You look like a ... 
=============================
Hi Human!
You look like a ... 
=============================
This dog's breed is ...
=============================
This dog's breed is ...
=============================
This dog's breed is ...
=============================
Could not find anything interesting on your image :(
But if you ask, it looks like ...
=============================
Could not find anything interesting on your image :(
But if you ask, it looks like ...
=============================
Could not find anything interesting on your image :(
But if you ask, it looks like ...
=============================

Step X: Going further with object detection :)

One of the improvements I wanted to make is to support many dogs/humans on the image and predict breed for each of them. Detecting object bounding box is more difficult than simply classifying an image. There're multiple popular architectures for that like YOLO, SSD, RetinaNet.

Implementing and training these models end-to-end from scratch to show dog breeds is rather difficult and time-consuming, so I decided to make it 2 steps:

  1. Use some existing (pre-trained) implementation to detect humand and dogs with bounding boxes
  2. Crop the image according to detected boxes and pass to dog breed classifier implemented eariler

For step #1 following YOLOv3 implementation was found and used: https://github.com/ultralytics/yolov3 This is the latest version of YOLO architecture implemented with Pytorch and it also provides pre-trained weights trained on COCO dataset with 80 classes, with classes 0 and 16 being 'person' and 'dog', which we need for our app.

For step #2 additional code was done below, including run_app_v2 function that is similar to run_app.

NOTE: I'm not including 3rd-party code in my repo. Following commands should be used to checkout that code and download pre-trained weights.

In [24]:
#!git clone https://github.com/ultralytics/yolov3 yolov3 
#!cd yolov3 
#!bash weights/download_yolov3_weights.sh
#!cd ..
In [32]:
import sys

# Import 3rd-party code
# Path must match to one used in command above
yolov3_rel_path = 'yolov3'
yolov3_path = os.path.join(sys.path[0], yolov3_rel_path)
sys.path.append(yolov3_path)
from models import *
from utils.datasets import *
from utils.utils import *
from utils import torch_utils

# Wrapper around 3rd-party yolov3 implementation
class YOLOv3Lib():

    def __init__(self, yolov3_path, img_size=416, conf_thres=0.3, nms_thres=0.45):
        # paths
        self.net_config_path = os.path.join(yolov3_path, 'cfg/yolov3.cfg')
        self.data_config = parse_data_cfg(os.path.join(yolov3_path, 'cfg/coco.data'))
        self.classes = load_classes(os.path.join(yolov3_path, self.data_config['names']))
        self.weights_path = os.path.join(yolov3_path, 'weights/yolov3.weights')

        self.img_size = img_size
        self.conf_thres = conf_thres
        self.nms_thres = nms_thres

        # Load model
        self.model = Darknet(self.net_config_path, self.img_size)
        load_darknet_weights(self.model, self.weights_path)
        self.model.eval()

    # Scale, pad and normalize the image
    # Returns padding info that can be used to "unpad" and "unscale" the image
    def prepare_img(self, img_path):
        img = Image.open(open(img_path, "rb"))
        # scale the image so that the smallest size will be img_size
        scale = min(self.img_size/img.size[0], self.img_size/img.size[1])
        width = round(img.size[0] * scale)
        height = round(img.size[1] * scale)
        # center-pad from left/right
        pad_left = (self.img_size - width) // 2
        pad_right = self.img_size - width - pad_left
        # no padding from top, just bottom
        pad_top = 0
        pad_bottom = self.img_size - height
        pad = (pad_left, pad_top, pad_right, pad_bottom)
        img_transforms = transforms.Compose([
            transforms.Resize((height, width)),
            transforms.Pad(pad, (128,128,128)),
            transforms.ToTensor(),
        ])
        input_img = img_transforms(img).unsqueeze(0)
        return input_img, img, (scale, pad_left)

    # Detect objects and crop pieces of original image that correspond to detected classes
    def extract_classes(self, img_path, return_classes = [0, 16]):
        input_img, img, (scale, pad_left) = self.prepare_img(img_path)
        with torch.no_grad():
            pred = self.model(input_img)

        res = []
        # Keep only items that exceed confidence thresholds and non-max suppression threshold
        pred = pred[pred[:, :, 4] > self.conf_thres]
        detections = non_max_suppression(pred.unsqueeze(0), self.conf_thres, self.nms_thres)

        for x1, y1, x2, y2, conf, cls_conf, cls_pred in detections[0]:
            # return only classes we need
            if not int(cls_pred) in return_classes: continue
            # remove left padding
            x1, x2 = x1 - pad_left, x2 - pad_left
            # restore to orig image size
            x1, x2, y1, y2 = x1/scale, x2/scale, y1/scale, y2/scale
            # check for min/max boundaries
            x1, y1, x2, y2 = max(x1, 0), max(y1, 0), max(x2, 0), max(y2, 0)
            x1, y1, x2, y2 = min(x1, img.size[0]), min(y1, img.size[1]), min(x2, img.size[0]), min(y2, img.size[1])
            # crop the piece of image
            piece = img.crop((int(x1),int(y1),int(x2),int(y2)))
            res.append((piece, self.classes[int(cls_pred)]))
                                            
        return res
    
yolo = YOLOv3Lib(yolov3_path)
In [33]:
from IPython.core.display import display, HTML

# V2 of app
def run_app_v2(img_path):
    # detect persons and dogs (0, 16) with YOLO
    images = yolo.extract_classes(img_path, [0, 16])

    if len(images) == 0:
        print("Could not find anything interesting on your image :(")
        plt.imshow(Image.open(img_path))
        plt.show()
        return
    else:
        print("Found %d objects on your image!" % len(images))
        plt.imshow(Image.open(img_path))
        plt.show()
    
    for img, cls in images:
        # Predict breed
        dog_class = predict_breed_transfer(img)
        dog_class_link = HTML("<a href='https://www.google.com/search?tbm=isch&q=%(dog)s'>%(dog)s</a>" % {'dog': dog_class })
        if cls == "person":
            print("I think I found a person:")
            plt.imshow(img)
            plt.show()
            print("And this person looks like a ... ")
            display(dog_class_link)
        elif cls == "dog":
            print("This should be a dog:")
            plt.imshow(img)
            plt.show()
            print("And the dog's breed is ...")
            display(dog_class_link)
        else:
            # unknown class
            print("Not sure what is that:")
            plt.imshow(img)
            plt.show()
            print("But if you ask, it looks like ...")
            display(dog_class_link)
In [34]:
from glob import glob
for file in glob('test/**/*.jpg'):
    run_app_v2(file)
    print('=============================')
Found 1 objects on your image!
This should be a dog:
And the dog's breed is ...
=============================
Found 1 objects on your image!
This should be a dog:
And the dog's breed is ...
=============================
Found 1 objects on your image!
This should be a dog:
And the dog's breed is ...
=============================
Found 2 objects on your image!
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
=============================
Found 2 objects on your image!
This should be a dog:
And the dog's breed is ...
I think I found a person:
And this person looks like a ... 
=============================
Found 1 objects on your image!
This should be a dog:
And the dog's breed is ...
=============================
Found 24 objects on your image!
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
=============================
Found 12 objects on your image!
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
This should be a dog:
And the dog's breed is ...
=============================
Found 1 objects on your image!
I think I found a person:
And this person looks like a ... 
=============================
Found 1 objects on your image!
I think I found a person:
And this person looks like a ... 
=============================
Found 1 objects on your image!
I think I found a person:
And this person looks like a ... 
=============================
Found 1 objects on your image!
I think I found a person:
And this person looks like a ... 
=============================
Found 1 objects on your image!
I think I found a person:
And this person looks like a ... 
=============================
Found 1 objects on your image!
This should be a dog:
And the dog's breed is ...
=============================
Found 1 objects on your image!
This should be a dog:
And the dog's breed is ...
=============================
Found 2 objects on your image!
I think I found a person:
And this person looks like a ... 
This should be a dog:
And the dog's breed is ...
=============================
Found 2 objects on your image!
This should be a dog:
And the dog's breed is ...
I think I found a person:
And this person looks like a ... 
=============================
Could not find anything interesting on your image :(
=============================
Found 1 objects on your image!
This should be a dog:
And the dog's breed is ...
=============================
In [ ]: